Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific time references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    жÑĥ
    -0.15
    esian
    -0.14
    ļĮ
    -0.14
    _deinit
    -0.14
    yor
    -0.14
    dete
    -0.14
    REFERENCE
    -0.14
    ade
    -0.13
    Ñĥж
    -0.13
    adier
    -0.13
    POSITIVE LOGITS
     around
    0.43
    around
    0.36
     approximately
    0.29
    Around
    0.29
     Around
    0.29
     about
    0.27
     shortly
    0.26
    -around
    0.25
     kolem
    0.22
     precisely
    0.22
    Act Density 0.043%

    No Known Activations